KR20200028089A - Electronic apparatus and controlling method thereof - Google Patents

Abstract

Disclosed is a control method of an electronic apparatus. The control method comprises the steps of: using the electronic apparatus and obtaining at least one keyword in content of a call with a user of another electronic apparatus while having a call with the user of another electronic apparatus; displaying the at least one keyword while the call is performed; and providing a search result for a keyword selected by a user of the at least one displayed keyword. In particular, at least a part of the control method of the present invention may use an artificial intelligence model trained in accordance with at least one of machine learning, neural networks, or deep learning algorithms.

Description

Electronic device and control method thereof {ELECTRONIC APPARATUS AND CONTROLLING METHOD THEREOF}

The present disclosure relates to an electronic device and a control method thereof, and more particularly, to an electronic device and a control method thereof that can acquire at least one keyword from a call content and utilize it for various functions.

In addition, the present disclosure relates to an artificial intelligence (AI) system utilizing a machine learning algorithm and its application.

In recent years, artificial intelligence systems that embody human-level intelligence have been used in various fields. The artificial intelligence system is a system in which a machine learns, judges, and becomes smart unlike a rule-based smart system. As the artificial intelligence system is used, the recognition rate is improved and the user's taste can be more accurately understood, and the existing rule-based smart system is gradually being replaced by a deep learning-based artificial intelligence system.

Artificial intelligence technology is composed of machine learning (eg, deep learning) and elemental technologies utilizing machine learning.

Machine learning is an algorithm technology that classifies / learns the characteristics of input data by itself, and element technology is a technology that simulates functions such as cognition and judgment of the human brain by using machine learning algorithms such as deep learning. It consists of technical fields such as understanding, reasoning / prediction, knowledge expression, and motion control.

The various fields in which artificial intelligence technology is applied are as follows. Linguistic understanding is a technology that recognizes and applies / processes human language / characters, and includes natural language processing, machine translation, conversation system, question and answer, and speech recognition / synthesis. Visual understanding is a technique of recognizing and processing objects as human vision, and includes object recognition, object tracking, image search, human recognition, scene understanding, spatial understanding, and image improvement. Inference prediction is a technique for logically inferring and predicting information by determining information, and includes knowledge / probability-based reasoning, optimization prediction, preference-based planning, and recommendation. Knowledge expression is a technology that automatically processes human experience information into knowledge data, and includes knowledge building (data generation / classification), knowledge management (data utilization), and so on. Motion control is a technique for controlling autonomous driving of a vehicle and movement of a robot, and includes motion control (navigation, collision, driving), operation control (behavior control), and the like.

Recently, for efficient management of information and various user experiences, an artificial intelligence personal assistant platform has been provided on an electronic device.

On the other hand, while the user is making a call on an electronic device such as a smartphone, and after making a call, the user performs a task such as recording the call log or performing a web search based on the call log. This includes logging calls to applications such as applications, calendar applications, schedule applications, and browsing related information in a web browser. These tasks are cumbersome. However, in the conventional electronic device, there was no function to replace such a series of tasks, and the AI personal assistant platform also had a passive limitation because it was a structure in which a user had to directly issue a command.

An object of the present disclosure is to provide an electronic device and a control method thereof that can acquire at least one keyword from a call content and utilize it for various functions.

A control method of an electronic device according to an embodiment of the present disclosure may acquire at least one keyword in a content of a call with a user of another electronic device while performing a call with a user of another electronic device using the electronic device And displaying the at least one keyword while the call is being performed, and providing a search result for a keyword selected by the user among the displayed at least one keyword.

In this case, the displaying step may display the at least one keyword on a call screen with a user of the other electronic device.

Meanwhile, in the displaying, at least one circular UI element including each of the at least one keyword may be displayed.

In this case, the control method according to the present embodiment further includes determining the importance of the at least one keyword according to the number of times mentioned in a call with the user of the other electronic device, and the displaying step comprises: The size of the at least one circular UI element may be differently displayed according to the determined importance of the at least one keyword.

On the other hand, in the displaying step, when the obtained at least one keyword is plural, the arrangement interval of the plurality of keywords is determined according to the interval mentioned in the call with the user of the other electronic device, and according to the determined arrangement interval. The plurality of keywords can be displayed.

On the other hand, in the control method according to the present embodiment, when there is a plurality of at least one keyword displayed, when a user input for sequentially selecting two or more keywords among the plurality of keywords is received, the selected two or more keywords are set as one set. The method may further include a step of determining, and the step of providing the search result may provide the search result for the determined set.

In this case, the control method according to the present embodiment further includes displaying a first UI element corresponding to the search function for the determined set and a second UI element corresponding to the memo function for the determined set, In the step of providing the search result, when the first UI element is selected, the search result for the determined set may be provided.

In this case, the control method according to the present embodiment may further include storing the determined set in the memo application when the second UI element is selected.

Meanwhile, the acquiring step may acquire at least one keyword from the content of a call with a user of the other electronic device using the learned artificial intelligence model.

On the other hand, the control method according to the present embodiment, when the call with the user of the other electronic device ends, determining a recommended application among the plurality of applications of the electronic device based on the obtained at least one keyword and the The method may further include displaying a UI inquiring whether to perform a task related to the determined recommended application and the obtained at least one keyword.

On the other hand, in the electronic device according to an embodiment of the present disclosure, a communication unit, a display, a memory for storing computer executable instructions (computer executable instructions), and executing the computer executable instructions, other electronics using the electronic device While performing a call with a user of the device, acquire at least one keyword from the content of a call with the user of the other electronic device, control the display to display the at least one keyword while the call is being performed, and display the And a processor that provides a search result for a keyword selected by a user among at least one keyword.

In this case, the processor may control the display to display the at least one keyword on a call screen with a user of the other electronic device.

Meanwhile, the processor may control the display to display at least one circular UI element each including the at least one keyword.

In this case, the processor determines the importance of the at least one keyword according to the number of times mentioned in a call with the user of the other electronic device, and determines the importance of the at least one keyword according to the determined importance of the at least one keyword. The display can be controlled to display different sizes of UI elements.

On the other hand, when the plurality of the at least one keyword is obtained, the processor determines the spacing of the plurality of keywords according to the interval mentioned in the call with the user of the other electronic device, and the plurality of keywords according to the determined placement interval. The display may be controlled to display a keyword of.

On the other hand, when the plurality of at least one keyword displayed is the processor, when a user input for sequentially selecting two or more keywords among the plurality of keywords is received, the processor determines the selected two or more keywords as a set, and the determined You can provide search results for sets.

In this case, the processor controls the display to display a first UI element corresponding to a search function for the determined set and a second UI element corresponding to a memo function for the determined set, and the first UI element When is selected, a search result for the determined set may be provided.

In this case, when the second UI element is selected, the processor may store the determined set in a memo application.

Meanwhile, the processor may acquire at least one keyword from the content of a call with a user of the other electronic device using the learned artificial intelligence model.

Meanwhile, when the call with the user of the other electronic device ends, the processor determines a recommended application among the plurality of applications of the electronic device based on the obtained at least one keyword, and the determined recommended application and the acquisition The display may be controlled to display a UI inquiring whether to perform a task related to at least one keyword.

1 is a view for explaining an electronic device displaying keywords obtained from a call according to an embodiment of the present disclosure;
2 to 3 are diagrams for explaining the configuration of an electronic device according to various embodiments of the present disclosure;
4 to 5 is a view for explaining an embodiment of the present disclosure to obtain a keyword in the call content and display the obtained keyword on the call screen,
6 is a view for explaining an embodiment of the present disclosure for selecting keywords displayed on a call screen,
7 is a view for explaining a UI according to an embodiment of the present disclosure providing a memo function or a search function with selected keywords,
8 is a view for explaining an embodiment of the present disclosure in which a screen is displayed on a call screen as a result of searching by keywords acquired in a call;
9 to 10 are views for explaining an embodiment of the present disclosure in which keywords are changed in real time on a call screen in real time according to the content of a call;
11 is a view for explaining a UI according to another embodiment of the present disclosure providing a memo function or a search function with selected keywords;
12 is a view for explaining an embodiment of the present disclosure for registering a memo with keywords obtained in a currency;
13 is a view for explaining a UI according to an embodiment of the present disclosure recommending an action that can be performed with keywords obtained in a call immediately after the call ends;
14 is a view for explaining an embodiment of the present disclosure to provide personalized information with keywords obtained from a currency,
15 is a view for explaining the overall structure of a service that provides various functions by obtaining keywords in a call according to an embodiment of the present disclosure;
16 is a block diagram illustrating a processor for learning and using a recognition model, according to an embodiment of the present disclosure;
17 to 19 are block diagrams illustrating a learning unit and an analysis unit according to various embodiments of the present disclosure;
20 is a flowchart of a network system using an artificial intelligence model according to an embodiment of the present disclosure, and
21 is a flowchart illustrating a method of controlling an electronic device according to an embodiment of the present disclosure.

Hereinafter, various embodiments of the present document will be described with reference to the accompanying drawings. However, this is not intended to limit the techniques described in this document to specific embodiments, and should be understood to include various modifications, equivalents, and / or alternatives of embodiments of the document. . In connection with the description of the drawings, similar reference numerals may be used for similar components.

In this document, expressions such as "have," "can have," "includes," or "can contain," the existence of a corresponding feature (eg, a component such as a numerical value, function, operation, or part) And does not exclude the presence of additional features.

In this document, expressions such as “A or B,” “at least one of A or / and B,” or “one or more of A or / and B”, etc. may include all possible combinations of the items listed together. . For example, “A or B,” “at least one of A and B,” or “at least one of A or B,” (1) includes at least one A, (2) includes at least one B, Or (3) all cases including both at least one A and at least one B.

Expressions such as "first," "second," "first," or "second," as used herein may modify various components, regardless of order and / or importance, and denote one component. It is used to distinguish from other components, but does not limit the components. For example, the first user device and the second user device may indicate different user devices regardless of order or importance. For example, the first component may be referred to as a second component without departing from the scope of rights described in this document, and similarly, the second component may also be referred to as a first component.

The terms "module", "unit", and "part" used in this document are terms used to refer to components that perform at least one function or operation, and these components are implemented in hardware or software. Or it may be implemented as a combination of hardware and software. In addition, a plurality of "modules", "units", "parts", etc., are integrated into at least one module or chip, except that each needs to be implemented with individual specific hardware. Can be implemented as

Some component (eg, first component) is "(functionally or communicatively) coupled with / to" another component (eg, second component), or " When referred to as "connected to", it should be understood that any of the above components may be directly connected to the other component or may be connected through another component (eg, a third component). On the other hand, when it is mentioned that a component (eg, a first component) is “directly connected” or “directly connected” to another component (eg, a second component), the component and the component It can be understood that other components (eg, the third component) do not exist between the other components.

As used herein, the expression "configured to" is, depending on the context, for example, "having the capacity to" , "" Designed to, "" adapted to, "" made to, "or" capable of "can be used interchangeably. The term "configured (or set) to" may not necessarily mean only "specifically designed to" in hardware. Instead, in some situations, the expression "a device configured to" may mean that the device "can" with other devices or parts. For example, the phrase “processors configured (or set) to perform A, B, and C” means by executing a dedicated processor (eg, an embedded processor) to perform the operation, or one or more software programs stored in the memory device. , It may mean a general-purpose processor (eg, CPU or application processor) capable of performing the corresponding operations.

The terms used in this document are only used to describe specific embodiments, and may not be intended to limit the scope of other embodiments. Singular expressions may include plural expressions unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by a person skilled in the art described in this document. Among the terms used in this document, terms defined in the general dictionary may be interpreted as having the same or similar meaning in the context of the related art, and are ideally or excessively formal, unless explicitly defined in this document. Is not interpreted as In some cases, terms defined in this document cannot be interpreted to exclude embodiments of the document.

An electronic device according to various embodiments of the present disclosure includes, for example, a smart phone, a tablet personal computer (PC), a mobile phone, a video phone, and an e-book reader. Desktop PC (desktop personal computer), laptop PC (laptop personal computer), netbook computer (netbook computer), workstation (workstation), server, PDA (personal digital assistant), PMP (portable multimedia player), MP3 player, mobile medical It may include at least one of a device, a camera, or a wearable device. According to various embodiments, the wearable device may be an accessory type (for example, a watch, ring, bracelet, anklet, necklace, glasses, contact lens, or head-mounted device (HMD)), a fabric or clothing integrated type ( Examples may include at least one of an electronic garment), a body attachment type (eg, a skin pad or a tattoo), or a bio-implantable type (eg, an implantable circuit).

In some embodiments, the electronic device may be a home appliance. Household appliances include, for example, televisions, digital video disk (DVD) players, audio, refrigerators, air conditioners, vacuum cleaners, ovens, microwave ovens, washing machines, air cleaners, set-top boxes, and home automation controls. Home automation control panel, security control panel, TV box (eg Samsung HomeSync ™, Apple TV ™, or Google TV ™, game console (eg Xbox ™, PlayStation ™, electronic dictionary, electronics) It may include at least one of a key, a camcorder, or an electronic picture frame.

In another embodiment, the electronic device includes various medical devices (eg, various portable medical measurement devices (such as a blood glucose meter, heart rate monitor, blood pressure meter, or body temperature meter), magnetic resonance angiography (MRA), magnetic resonance imaging (MRI), Computed tomography (CT), camera, or ultrasound, etc., navigation device, global navigation satellite system (GNSS), event data recorder (EDR), flight data recorder (FDR), automotive infotainment ) Devices, marine electronic equipment (e.g. marine navigation devices, gyro compasses, etc.), avionics, security devices, head units for vehicles, industrial or household robots, automatic teller's machines (ATMs) in financial institutions , Point of sales (POS) in stores, or Internet of things (e.g. light bulbs, various sensors, electricity or gas meters, sprinkler devices, fire alarms, thermostats, street lights, soil It may include at least one of a (aster), exercise equipment, hot water tank, heater, boiler, and the like.

According to some embodiments, the electronic device may be a furniture or part of a building / structure, an electronic board, an electronic signature receiving device, a projector, or various measuring devices (eg, Water, electricity, gas, or radio wave measurement devices, etc.). In various embodiments, the electronic device may be a combination of one or more of the various devices described above. The electronic device according to an embodiment may be a flexible electronic device. In addition, the electronic device according to the embodiment of the present document is not limited to the above-described devices, and may include a new electronic device according to technological development.

One object of the present disclosure is to provide an electronic device equipped with an artificial intelligence agent system for controlling keyword-based personalized recommendation information by obtaining a keyword from a call content and performing a related command, and a control method thereof.

Specifically, according to embodiments of the present disclosure, the electronic device may perform a simple search and memo function, for example, based on keywords obtained from a call during a call. In addition, immediately after the call, an application predicted to be used by the user may be determined based on the keyword obtained from the call and executed in association with the acquired keyword. In addition, the keywords obtained in the currency may be stored to provide personalized information based on the keywords at any time.

Hereinafter, the present disclosure will be described in more detail with reference to the drawings.

1 is a view for explaining an electronic device according to an embodiment of the present disclosure to obtain and provide keywords in a call with a counterpart.

Referring to FIG. 1, a user may perform a call with a user of another electronic device using the electronic device 100. During the call, the electronic device 100 may display keywords obtained in the call on the call screen with the other party. The displayed keywords are selectable UI elements. When the user selects a keyword, various functions may be executed based on the selected keyword. For example, a search function may be performed based on the selected keyword, and a memo function may be performed based on the selected keyword.

After the call is over, the electronic device 100 applies (or inputs) the acquired keywords to an application (note application, calendar application, schedule application, search application, etc.) that the user is expected to execute based on the acquired keywords. You can provide a UI that asks if you want to perform a task.

In addition, the electronic device 100 stores keywords obtained in the call and may provide personalized information based on the keywords obtained in the call at any time according to a user request.

2 is a block diagram illustrating a configuration of an electronic device 100 according to an embodiment of the present disclosure.

Referring to FIG. 2, the electronic device 100 includes a communication unit 110, a memory 120, a processor 130, and a display 140. Depending on the embodiment, some of the components may be omitted, and although not illustrated, appropriate hardware / software components of a level apparent to those skilled in the art may be additionally included in the electronic device 100.

The communication unit 110 may be connected to a network through, for example, wireless communication or wired communication to communicate with an external device. Wireless communication is, for example, a cellular communication protocol, for example, long-term evolution (LTE), LTE Advance (LTE-A), code division multiple access (CDMA), wideband CDMA (WCDMA), universal (UMTS) Mobile telecommunications system), WiBro (Wireless Broadband), or GSM (Global System for Mobile Communications) may be used. Further, the wireless communication may include short-range communication, for example. The short-range communication may include, for example, at least one of WiFi direct, Bluetooth, near field communication (NFC), and Zigbee. The wired communication may include, for example, at least one of a universal serial bus (USB), a high definition multimedia interface (HDMI), a recommended standard232 (RS-232), or a plain old telephone service (POTS). The network may include at least one of a telecommunications network, for example, a computer network (eg, LAN or WAN), the Internet, or a telephone network.

The communication unit 110 may include, for example, a cellular module, a WiFi module, a Bluetooth module, a GNSS module (eg, a GPS module, a Glonass module, a Beidou module, or a Galileo module), an NFC module, and a radio frequency (RF) module. .

The cellular module may provide, for example, a voice call, a video call, a text service, or an internet service through a communication network. According to an embodiment, the cellular module may perform identification and authentication of an electronic device in a communication network using a subscriber identification module (eg, a SIM card). According to an embodiment, the cellular module may perform at least some of the functions that the processor can provide. According to an embodiment, the cellular module may include a communication processor (CP).

Each of the WiFi module, the Bluetooth module, the GNSS module, or the NFC module, for example, may include a processor for processing data transmitted and received through a corresponding module. According to some embodiments, at least some (eg, two or more) of a cellular module, a WiFi module, a Bluetooth module, a GNSS module, or an NFC module may be included in one integrated chip (IC) or IC package.

The RF module, for example, may transmit and receive communication signals (eg, RF signals). The RF module may include, for example, a transceiver, a power amp module (PAM), a frequency filter, a low noise amplifier (LNA), or an antenna. According to another embodiment, at least one of a cellular module, a WiFi module, a Bluetooth module, a GNSS module, or an NFC module may transmit and receive an RF signal through a separate RF module.

The memory 120 may include, for example, internal memory or external memory. The internal memory includes, for example, volatile memory (eg, dynamic RAM (DRAM), static RAM (SRAM), or synchronous dynamic RAM (SDRAM)), non-volatile memory (eg, OTPROM (one time programmable ROM (PROM), programmable ROM (PROM), erasable and programmable ROM (EPROM), electrically erasable and programmable ROM (EEPROM), mask ROM, flash ROM, flash memory (e.g. NAND flash or NOR flash, etc.), hard drives, Or it may include at least one of a solid state drive (SSD).

The external memory is a flash drive, for example, compact flash (CF), secure digital (SD), micro secure digital (Micro-SD), mini secure digital (Mini-SD), extreme digital (xD), It may include a multi-media card (MMC) or a memory stick.

The memory 120 is accessed by the processor 130, and data read / write / modify / delete / update may be performed by the processor 130.

In the present disclosure, the term memory may include at least one of a memory provided separately from the processor 130, a ROM (not shown), and a RAM (not shown) in the processor 130.

The memory 120 may store trained artificial intelligence models, learning data, and the like.

The memory 120 may store various applications such as a memo application, a schedule application, a calendar application, a web browser application, and a call application.

The display 140 is configured to output an image. The display 140 is, for example, a liquid crystal display (LCD), a light-emitting diode (LED) display, an organic light-emitting diode (OLED) display (such as AMOLED) (active-matrix organic light-emitting diode), PMOLED (passive-matrix OLED), or microelectromechanical systems (MEMS) display, or electronic paper display. The display 140 may be implemented as a touch screen.

The processor 130 is a component for controlling the overall operation of the electronic device 100. For example, the processor 130 may drive an operating system and an application to control a number of hardware or software components connected to the processor 130, and may perform various data processing and calculations. The processor 130 may be a central processing unit (CPU) or graphics-processing unit (GPU), or both. The processor 250 may be implemented by at least one general-purpose processor, digital signal processor, application specific integrated circuit (ASIC), system on chip (SoC), microcomputer (MICOM), or the like.

The processor 130 may perform various calculations using the learned artificial intelligence model. For example, the processor 130 may acquire at least one keyword in a call with a counterpart performed using the electronic device 100 using the learned artificial intelligence model. According to an embodiment of the present disclosure, the processor 130 may acquire unique nouns by inputting the content of a call into a named entity recognition (NER) model, and select keywords from among the nouns. The acquired nouns mode may be selected as a keyword, or only those that satisfy a specific criterion among the acquired nouns may be selected as keywords. The specific criterion may be, for example, whether the number of times the proper noun is mentioned in a call is greater than or equal to a preset number of times, or whether the interval at which the proper noun is mentioned is less than a preset time. Alternatively, a proper noun belonging to a category corresponding to the keyword may be selected as a keyword. For example, categories such as time, person, and place may be categories corresponding to keywords. Alternatively, a keyword can be obtained by entering a proper noun into an artificial intelligence model trained to select a key keyword.

In the present disclosure, various AI models specialized for an application field may be used. The artificial intelligence model is a judgment model learned based on an artificial intelligence algorithm, and may be, for example, a model based on a neural network. The trained artificial intelligence model may be designed to simulate a human brain structure on a computer and may include a plurality of network nodes having weights, simulating neurons of a human neural network. A plurality of network nodes may each form a connection relationship so that neurons simulate synaptic activity of neurons that exchange signals through synapses. In addition, the trained artificial intelligence model may include, for example, a neural network model or a deep learning model developed from a neural network model. In the deep learning model, a plurality of network nodes may be located at different depths (or layers) and exchange data according to a convolution connection relationship. Examples of the learned artificial intelligence model may include, but are not limited to, Deep Neural Network (DNN), Recurrent Neural Network (RNN), and Bidirectional Recurrent Deep Neural Network (BRDNN).

The electronic device 100 may use a personal assistant program (eg, Bixby ™), which is a program dedicated to artificial intelligence (or an artificial intelligence agent). The personal assistant program is a dedicated program for providing AI (Artificial Intelligence) based services. Existing general-purpose processors (eg, CPUs) may be used for artificial intelligence processing, or single-purpose processors (eg, GPUs, FPGAs, ASICs, etc.) may be used. The electronic device 100 may include a plurality of processors, for example, a processor dedicated to artificial intelligence and other processors.

According to an embodiment of the present disclosure, a preset user input (for example, an icon touch corresponding to a personal assistant chatbot, a user voice including a preset word, etc.) is input or a button provided in the electronic device 100 ( For example, when the button for executing the AI agent) is pressed, the AI agent may operate (or execute). Alternatively, the AI agent may be in a standby state before a preset user input is detected or a button provided in the electronic device 100 is selected. Here, the standby state is a state of detecting that a predefined user input (eg, when a user's voice including a preset keyword (ex. Bixby) is input) is received to control the start of an AI agent operation. to be. When a preset user input is detected while the AI agent is in a standby state or a button provided in the electronic device 100 is selected, the electronic device 100 may operate the AI agent. Then, the artificial intelligence agent may perform the function of the electronic device 100 based on the voice when the user voice is received, and may output an answer if the voice is an inquiry voice.

Operations based on artificial intelligence may be performed within the electronic device 100, or may be performed through an external server. In the latter case, the artificial intelligence model is stored in the server, and the electronic device 100 provides data to be input to the artificial intelligence model as a server, and the server inputs data to the artificial intelligence model to transmit the result data obtained by the electronic device ( 100).

3 is a block diagram illustrating a configuration of an electronic device 100 according to another embodiment of the present disclosure. 3, the electronic device 100 includes a communication unit 110, a memory 120, a processor 130, a display 140, an input unit 150, an audio output unit 160, a microphone 170 It may include. Depending on the embodiment, some of the components may be omitted, and although not illustrated, appropriate hardware / software components of a level apparent to those skilled in the art may be additionally included in the electronic device 100. Meanwhile, since the communication unit 110, the memory 120, the processor 130, and the display 140 are described in FIG. 2, redundant description will be omitted.

The microphone 170 is configured to receive a user voice or other sound and convert it into a digital signal. The processor 130 may acquire at least one keyword from a call voice input through the microphone 170. The microphone 170 may be provided inside the electronic device 100, but this is only an example, and may be provided outside the electronic device 100 to be electrically connected to the electronic device 100.

The input unit 150 may receive a user input and transmit it to the processor 130. The input unit 150 may include, for example, a touch sensor, a (digital) pen sensor, a pressure sensor, a key, or a microphone. For the touch sensor, for example, at least one of capacitive, pressure-sensitive, infrared, and ultrasonic methods may be used. The (digital) pen sensor may be, for example, a part of the touch panel or may include a separate recognition sheet. The key may include, for example, a physical button, an optical key, or a keypad.

The touch sensor of the display 140 and the input unit 150 may be implemented as a touch screen by forming a mutual layer structure.

The audio output unit 160 may output an audio signal. For example, the voice output of the other party received through the audio output unit 160 and the communication unit 110 may be output. Also, the audio output unit 160 may output audio data stored in the memory 120. For example, the sound output unit 160 may output various notification sounds and may output the voice of an artificial intelligence assistant. The audio output unit 160 may include a receiver, a speaker, and a buzzer.

The memory 120 stores computer executable instructions, and when it is executed by the processor 130, a control method of the electronic device 100 described in the present disclosure may be performed.

For example, the processor 130 may acquire at least one keyword in a call with a user of another electronic device while performing a call with a user of another electronic device through the communication unit 110 by executing computer-executable instructions. The display 140 may be controlled to display the displayed keyword while the call is being performed.

During the call, the processor 130 collects the voice of the user input through the microphone and the voice of the other party of the other electronic device received through the communication unit 110, converts the collected voice into text, and keywords from the converted text Can be obtained.

In this case, the processor 130 may acquire at least one keyword in a call with a user of another electronic device using the learned artificial intelligence model.

According to another embodiment, the processor 130 may obtain at least one keyword in a call with a user of another electronic device based on a rule. For example, the processor 130 may acquire at least one keyword based on the frequency of words mentioned in a call with a user of another electronic device, the strength of the sound speaking the word, and the like.

An embodiment of the present disclosure for obtaining a keyword in a currency will be described with reference to FIGS. 4 to 5.

4 illustrates the content of a call between a user 10 of the electronic device 100 and a user 20 of another electronic device.

The processor 130 may acquire at least one keyword (indicated by an underline) from the content of the call in which the call is performed. For example, the processor 130 may acquire nouns such as "tomorrow", "7 o'clock", "dongnam brother", "gangnam station", "gourmet" as keywords.

And referring to FIG. 5, the processor 130 may control the display 140 to display at least one keyword. In this case, the processor 130 may control the display 140 to display at least one keyword acquired on the call screen 500 with the user 20 of another electronic device. The call screen 500 is a screen displayed on the display 140 during a call with a user 20 of another electronic device, and includes information such as the name and contact information of the user 20 of the other electronic device. , It may include a button UI corresponding to functions such as talking on the speaker, hang up the phone, mute, and the like.

According to an embodiment, the processor 130 may control the display 140 to display at least one UI element 51 to 58 each including at least one keyword obtained in a call. The at least one UI element 51 to 58 may be circular, specifically, a bubble shape. However, the shape of the UI element including the keyword is not particularly limited. For example, a UI element including a keyword may have a quadrangular shape.

The processor 130 may display the sizes of at least one UI element 51 to 58 including the keyword differently according to the importance of the keyword contained therein. That is, in the case of a UI element containing a keyword with high importance, the size of the UI element containing a keyword with low importance can be expressed in a larger size. For example, referring to FIG. 5, UI elements 51, 54, 56, and 58 that include keywords with relatively high importance are UI elements 52, 53, 55, and 57 that contain keywords with relatively low importance. ).

According to an embodiment, the processor 130 may input keywords into the learned artificial intelligence model to obtain information about the importance of the keywords.

According to another embodiment, the processor 130 may determine the importance of the keyword according to the weight set differently for each category. For example, when weights (numbers in parentheses) are set, such as the time category 5, person category 4, and place category 2, keywords belonging to the time category have higher importance than keywords belonging to the place category.

 According to another embodiment, the processor 130 may determine the importance according to the number of times the keyword is mentioned in the currency. That is, the greater the number of times mentioned, the higher the importance.

According to an embodiment, the processor 130 may control to display only a certain number of keywords on the call screen 500. In this case, it is possible to control such that only a few keywords having high importance are displayed.

In addition, keywords displayed on the call screen 500 may disappear from the call screen 500 according to user manipulation. When a specific keyword disappears, another new keyword may be displayed on the call screen 500. For example, a new keyword having the next importance level may be displayed on the call screen 500.

For example, if there is a user input for removing any one of the UI elements 51 to 58 including the keyword, the processor 130 removes the corresponding UI element from the call screen 500, and generates a keyword having the next importance level. Including UI elements may be displayed on the call screen 500.

The user input for removing the UI element may be, for example, a user's touch motion that selects the UI element and moves it out of the call screen 500. As another example, it may be a user input that double-touches a UI element. In addition, various user inputs are possible. According to an embodiment, when the UI elements 51 to 58 have a bubble shape, a graphic effect in which the bubble bursts when removed may be provided.

On the other hand, in order to more intuitively grasp the association between keywords, the processor 130 may arrange keywords according to the degree of association between the keywords. According to an embodiment of the present disclosure, the processor 130 determines a placement interval of a plurality of keywords according to the interval mentioned in the call with the user 20 of another electronic device, and displays 140 to display a plurality of keywords at the determined placement interval. ) Can be controlled.

According to this embodiment, keywords mentioned together may be displayed adjacently. For example, if the currency includes the phrase "How about Gangnam Station at 7:00 tomorrow?", The UI element 55 including the keyword "tomorrow", the UI element 51 including the keyword "7 o'clock", the keyword UI elements 56 including "Gangnam Station" may be displayed at positions adjacent to each other.

The user 10 can intuitively know which topic the conversation is under, while watching the keywords displayed on the call screen 500 while making a call. In addition to this, keywords obtained from currencies can be used for various functions.

According to an embodiment of the present disclosure, the processor 130 may apply a keyword selected by a user among at least one keyword displayed on the display 140 to an application of the electronic device 100 to perform a function related to the keyword in the application. .

For example, the processor 130 may provide a search result for a keyword selected by a user among at least one keyword displayed on the display 140. As another example, the processor 130 may register a keyword selected by the user from at least one keyword displayed on the display 140 to the memo application. In addition, various functions may be provided.

On the other hand, if the user selects one keyword, it is also possible to execute the function using one keyword, but when the user selects two or more keywords, it is also possible to execute the function using two or more keywords.

Various methods may be used as a method of selecting two or more keywords. For example, two or more keywords may be selected by various user operations, such as an operation of sequentially touching two or more keywords, an operation of simultaneously touching two or more keywords (multi-touch), a drag operation of two or more keywords, and the like.

6 illustrates an example of a method of selecting two or more keywords.

Referring to FIG. 6, the user performs the drag operation from the UI element 56 including the “Gangnam Station” and ends at the UI element 58 including the keyword “Gourmet Station” to perform the keywords “Gangnam Station” and “Gourmet Restaurant”. You can choose.

When a user input for selecting two or more keywords is received, the processor 130 may determine the selected two or more keywords as one set. In the case of FIG. 6, the processor 130 may determine the keywords “Gangnam Station” and “Gourmet Restaurant” as one set.

The electronic device 100 may search or make a note with the determined set. The description of this embodiment will be described with reference to FIG. 7.

7 is a view for explaining an embodiment of the present disclosure to perform a memo or search with a keyword selected by a user among keywords acquired in a currency.

When a user input for selecting two or more keywords is received as shown in FIG. 6, the processor 130 determines two or more keywords as a set, and as shown in FIG. 7, the user selects two or more keywords of the call screen 500. It can be displayed on one area 710.

Then, the processor 130 controls the display 140 to display the first UI element 720 corresponding to the memo function for the determined set and the second UI element 730 corresponding to the search function for the determined set. can do.

Here, when the first UI element 720 is selected, the processor 130 may store the keyword set in the memo application.

Here, when the second UI element 730 is selected, the processor 130 may provide a search result for the keyword set. For example, as illustrated in FIG. 8, search results 810 corresponding to “Gangnam Station” and “Delicious” may be provided. The search result 810 may also be provided on the call screen 500.

After performing search, memo, etc. through the call screen 500 as described above, the user 10 can continue the call as shown in FIG. 9 with the user 20 of another electronic device. The processor 130 may acquire keywords in real time in a call. Therefore, keywords displayed on the call screen 500 during a call may be changed in real time. FIG. 10 shows a call screen 500 after performing a call as shown in FIG. 9. It can be seen that the keywords displayed on the call screen 500 of FIG. 10 are different from the keywords displayed on the call screen 500 of FIG. 5.

And when the user performs a drag operation for selecting a plurality of keywords as shown in FIG. 10, the processor 130 determines the three keywords selected by the drag operation as a set, as shown in FIG. Similarly, three keywords selected by the user may be displayed on one area 710 of the call screen 500.

In this case, keywords in the region 710 may be arranged in a natural form according to the language structure. The processor 130 may arrange keywords according to keyword categories (time, place, activity). For example, the processor 130 may place a keyword (a tasting room) belonging to a place category after a keyword belonging to a time category (7 o'clock), and a keyword (reservation) belonging to an activity category after a keyword belonging to a place category.

The processor 130 displays 140 to display a first UI element 720 corresponding to a search function for a set of three keywords and a second UI element 730 corresponding to a memo function for a set of three keywords ) Can be controlled.

Here, when the first UI element 720 is selected, the processor 130 may store the keyword set in the memo application. For example, as illustrated in FIG. 12, the processor 130 may input and store the keyword set “7 o'clock tasting room reservation” in the memo application.

Meanwhile, when the call with the user of the other electronic device ends, the processor 130 determines a recommended application among the plurality of applications of the electronic device 100 based on at least one keyword obtained in the call, and the determined recommended application and The display 140 may be controlled to display a UI inquiring whether to perform an operation related to the obtained at least one keyword. In addition, when a UI for querying a job is selected, the processor 130 may perform the job.

The processor 130 may determine an application corresponding to a keyword (or a category of the obtained keyword) as a recommended application, based on a mapping list between the keyword (or a category of the keyword) and the application. The mapping list may be pre-stored in the memory 120.

For example, when the recommended application determined based on the keyword is a schedule application, the processor 130 may display a UI inquiring whether to perform a task of registering a keyword related to the schedule among the obtained at least one keyword to the schedule application. have. With respect to this embodiment, it will be described with reference to FIG. 13.

Referring to FIG. 13, when a call with a user 20 of another electronic device is completed, the processor 130 immediately inquires whether to perform a task of registering a keyword obtained in a call to a schedule application immediately after the call is completed. The display 140 may be controlled to display 1310. When the UI 1310 is selected, the processor 130 may perform a task of registering a schedule in the schedule application.

As another example, when the recommended application determined based on at least one keyword obtained in a currency is a remittance application, the processor 130 transmits the amount of the remittance based on a keyword related to a remittance amount among at least one keyword obtained. Through the application, the display 140 may be controlled to display a UI (ex. "Are you sure you want to proceed with the transfer of 15,000 won to Kim Young-hee?") Asking whether or not to perform a remittance.

As another example, when the recommended application determined based on at least one keyword obtained in a call is a contact application, the processor 130 may use the first contact stored in the contact application based on a keyword related to contact transfer among at least one keyword. The display 140 may be controlled to display a UI (ex. "Shall you send Kim Young-hee's contact with Kim Cheol-soo's contact?") Asking whether or not to perform the task of transmitting information about the second contact stored in the contact application. .

As another example, when the recommended application determined based on at least one keyword obtained in a call is a message application, the processor 130 transmits a character composed of keywords based on a keyword related to message transmission among at least one keyword. The display 140 may be controlled to display a UI inquiring whether to perform a task.

According to another embodiment of the present disclosure, personalized information may be provided based on at least one keyword acquired in a currency. An example of personalization information will be described with reference to FIG. 14.

14 illustrates a personalization information providing screen according to an embodiment of the present disclosure.

The electronic device 100 may provide personalized information based on user profile information. The user profile information may include, for example, a user name, age, gender, job, schedule, a user's movement path (path that the electronic device 100 traveled), and at least one keyword obtained from a call.

The electronic device 100 may provide information based on the user profile information. In particular, the electronic device 100 may provide information based on keywords acquired in a call. For example, as illustrated in FIG. 14, when the keywords “evening”, “7 o’clock”, and “Gangnam Station” are obtained in a call with a user of another electronic device, based on these keywords, the words “near 7 o'clock near Gangnam Station” 'Recommended things to play'. According to this embodiment, information that is more suited to the use context may be provided based on the content of the call.

15 is a view for explaining a service structure that provides various functions by obtaining keywords in a call according to an embodiment of the present disclosure.

Referring to FIG. 15, when a user makes a call with a user of another electronic device through the electronic device 100, a call voice (user's voice and voice of another electronic device) is input, and pre-processing of the input call voice Is performed and feature vectors can be obtained. Then, by inputting feature vectors into a trained artificial intelligence model, such as a named entity recognition (NER) model, unique nouns can be extracted from the voice of the call.

Also, the electronic device 100 may select keywords from the extracted nouns. At this time, the importance of the keyword may be considered. Also, the electronic device 100 may provide the selected keywords to the user, perform a search with the keyword selected by the user, or perform a memo function. Also, the electronic device 100 may perform deep learning-based action recommendation (eg, schedule registration, remittance, contact transfer, message (SMS) transmission, etc.) using the selected keywords.

The functions performed in the above-described embodiments may be performed using an artificial intelligence model. For example, functions such as acquiring keywords, determining importance for keywords, arranging keywords, and determining recommended applications based on keywords may be performed using an artificial intelligence model.

16 is a block diagram illustrating a processor for learning and using an artificial intelligence model according to an embodiment of the present disclosure.

Referring to FIG. 16, the processor 1600 may include at least one of a learning unit 1610 and an analysis unit 1620.

The learning unit 1610 may generate an artificial intelligence model having a judgment criterion using the learning data.

For example, the learning unit 1610 may generate and train an artificial intelligence model to acquire keywords from speech data as speech data as learning data.

The analysis unit 1620 may input a voice data into the artificial intelligence model to obtain keywords from the voice data. Functionally, the artificial intelligence model may include a speech to text (STT) module, a named entity recognition (NER) module, and a keyword selection module.

The STT (Speech to text) module converts the input voice into text. And the NER (Named entity recognition) module that receives the converted text can extract a proper noun from the text. In addition, the keyword selection module may select keywords by determining the importance of the extracted noun. The importance may be determined according to the weight of the proper noun or the weight of the category to which the proper noun belongs, the frequency of use of the proper noun, the interval between use of the proper noun, and the volume of the user's voice that utters the proper noun.

At least a portion of the learning unit 1610 and at least a portion of the analysis unit 1620 may be implemented as a software module or manufactured in the form of at least one hardware chip and mounted on an electronic device. For example, at least one of the learning unit 1610 and the analysis unit 1620 may be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), or an existing general-purpose processor (eg, CPU or application) It may be manufactured as part of a processor or a graphics-only processor (for example, a GPU) and mounted on a server that provides an analysis result to the aforementioned electronic device 100 or the electronic device 100.

At this time, the dedicated hardware chip for artificial intelligence is a dedicated processor specialized in probability calculation, and has higher parallel processing performance than a conventional general-purpose processor, and thus can rapidly perform computational tasks in the field of artificial intelligence such as machine learning. When the learning unit 1610 and the analysis unit 1620 are implemented as a software module (or a program module including an instruction), the software module is a computer-readable, non-transitory readable recording medium (non- transitory computer readable media). In this case, the software module may be provided by an operating system (OS) or may be provided by a predetermined application. Alternatively, some of the software modules may be provided by an operating system (OS), and the other may be provided by a predetermined application.

The learning unit 1610 and the analysis unit 1620 may be mounted on one electronic device, or may be mounted on separate electronic devices, respectively. For example, the processor 1600 of FIG. 16 may be the processor 130 of FIG. 2 or 3. As another example, one of the learning unit 1610 and the analysis unit 1620 may be included in the electronic device 100, and the other may be included in an external server. In addition, the learning unit 1610 and the analysis unit 1620 may provide model information constructed by the learning unit 1610 to the analysis unit 1620 through wired or wireless communication, or input to the learning unit 1610. Data may be provided to the learning unit 1610 as additional learning data.

17 is a block diagram of a learning unit 1610 according to an embodiment.

Referring to FIG. 17, the learning unit 1610 according to some embodiments may include a learning data acquisition unit 1610-1 and a model learning unit 1610-4. In addition, the learning unit 1610 may further include at least one of a learning data pre-processing unit 1610-2, a learning data selection unit 1610-3, and a model evaluation unit 1610-5.

The learning data acquisition unit 1610-1 may acquire learning data to train a model for keyword acquisition from speech data.

The learning data may be data collected or tested by the learning unit 1610 or the manufacturer of the learning unit 1610. For example, learning data may include voice or text.

The model learning unit 1610-4 may train the model to have a standard on how to understand, recognize, recognize, judge, reason, and the like, using input data. The model learning unit 1610-4 may train the model through supervised learning using at least a part of the training data as a judgment criterion. Alternatively, the model learning unit 1610-4, for example, learns the model by itself using learning data without much guidance, through unsupervised learning to discover judgment criteria for judgment of the situation. Can be learned. Also, the model learning unit 1610-4 may train the model, for example, through reinforcement learning using feedback on whether a result of situation determination according to learning is correct. In addition, the model learning unit 1610-4 may train a model using, for example, a learning algorithm including an error back-propagation or a gradient descent method.

The model learning unit 1610-4 may determine, as a model to learn, a model having a large relationship between input learning data and basic learning data when there are a plurality of pre-built models. In this case, the basic learning data may be pre-classified for each type of data, and the model may be pre-built for each type of data. For example, the basic learning data may be pre-classified based on various criteria such as a region where learning data is generated, a time when learning data is generated, a size of learning data, a genre of learning data, and a creator of learning data.

When the model is trained, the model learning unit 1610-4 may store the trained model. For example, the model learning unit 1610-4 may store the trained model in the memory 120 of the electronic device 100. Alternatively, the model learning unit 1610-4 may store the trained model in a memory of a server connected to the electronic device 100 through a wired or wireless network.

The learning unit 1610 further includes a learning data pre-processing unit 1610-2 and a learning data selection unit 1610-3 in order to improve the processing power of the model or to save resources or time required to generate the model. You may.

The learning data preprocessing unit 1610-2 may preprocess the acquired data so that the acquired data can be used for learning for situation determination. The learning data preprocessing unit 1610-2 may process the acquired data in a preset format so that the model learning unit 1610-4 can use the acquired data for learning for situation determination.

The learning data selection unit 1610-3 may select data necessary for learning from data acquired by the learning data acquisition unit 1610-1 or data pre-processed by the learning data pre-processing unit 1610-2. The selected learning data may be provided to the model learning unit 1610-4. The learning data selection unit 1610-3 may select learning data necessary for learning from acquired or preprocessed data according to a preset selection criterion. Further, the learning data selector 1610-3 may select learning data according to a preset selection criterion by learning by the model learning unit 1610-4.

The learning unit 1610 may further include a model evaluation unit 1610-5 to improve the processing power of the model.

The model evaluation unit 1610-5 may input evaluation data into the model, and when the result output from the evaluation data does not satisfy a predetermined criterion, the model learning unit 1610-4 may cause the model learning unit 1610-4 to train the model again. have. In this case, the evaluation data may be predefined data for evaluating the model.

For example, the model evaluation unit 1610-5 does not satisfy a predetermined criterion when the number or ratio of evaluation data in which the analysis result is not accurate among the analysis results of the trained model for the evaluation data exceeds a preset threshold. It can be evaluated as failed.

On the other hand, when there are a plurality of trained models, the model evaluator 1610-5 may evaluate whether or not a predetermined criterion is satisfied for each trained model, and determine a model that satisfies a predetermined criterion as a final model. In this case, when there are a plurality of models satisfying a predetermined criterion, the model evaluator 1610-5 may determine any one or a predetermined number of models preset in order of highest evaluation score as the final model.

Referring to FIG. 18, the analysis unit 1620 according to some embodiments may include a data acquisition unit 1620-1 and an analysis result providing unit 1620-4. In addition, the analysis unit 1620 may further include at least one of a data preprocessing unit 1620-2, a data selection unit 1620-3, and a model update unit 1620-5.

The data acquisition unit 1620-1 may acquire data necessary for analysis. The analysis result providing unit 1620-4 may provide the result of inputting the data acquired by the data acquisition unit 1620-1 to the trained model. The analysis result providing unit 1620-4 may provide analysis results according to the purpose of analyzing the data. The analysis result providing unit 1620-4 may obtain analysis results by applying data selected by the data pre-processing unit 1620-2 or data selection unit 1620-3, which will be described later, to the recognition model as input values. The results of the analysis can be determined by the model.

As an embodiment, the analysis result providing unit 1620-4 may acquire at least one keyword by applying the voice data acquired by the data acquisition unit 1620-1 to the artificial intelligence model.

The analysis unit 1620 may further include a data preprocessing unit 1620-2 and a data selection unit 1620-3 to improve the analysis results of the model or to save resources or time for providing analysis results. It might be.

The data preprocessing unit 1620-2 may preprocess the acquired data so that the acquired data can be used for situation determination. The data pre-processing unit 1620-2 may process the acquired data in a predefined format so that the analysis result providing unit 1620-4 can use the acquired data.

The data selection unit 1620-3 may select data required for situation determination from data acquired by the data acquisition unit 1620-1 or data preprocessed by the data preprocessing unit 1620-2. The selected data may be provided to the analysis result providing unit 1620-4. The data selector 1620-3 may select some or all of the obtained or preprocessed data according to a preset selection criterion for determining the situation. Further, the data selection unit 1620-3 may select data according to a preset selection criterion by learning by the model learning unit 1610-4.

The model updating unit 1620-5 may control the model to be updated based on the evaluation of the analysis results provided by the analysis result providing unit 1620-4. For example, the model updating unit 1620-5 provides the analysis result provided by the analysis result providing unit 1620-4 to the model learning unit 1610-4, so that the model learning unit 1610-4 You can ask the model to learn or update further.

19 is a diagram for explaining an embodiment in which the above-described learning unit 1610 and the analysis unit 1620 are implemented in different devices.

Referring to FIG. 19, the external server 200 may include a learning unit 1610, and the electronic device 100 may include an analysis unit 1620. The electronic device 100 and the server 200 may communicate with each other on the network.

The analysis result providing unit 1620-4 of the electronic device 100 may obtain the analysis result by applying the data selected by the data selection unit 1620-3 to the model generated by the server 200. In this case, the analysis result providing unit 1620-4 of the electronic device 100 receives the model generated by the server 200 from the server 200, and uses the received model to the user of the electronic device 100 And at least one keyword can be obtained in a call with the other party.

20 is a flowchart of a network system using an artificial intelligence model, according to various embodiments of the present disclosure.

In FIG. 20, a network system using an artificial intelligence model may include a first component 2010 and a second component 2020.

Here, the first component 2010 may be the electronic device 100. In addition, the second component 2020 may be a server in which the artificial intelligence model is stored. Alternatively, the first component 2010 may be a general-purpose processor, and the second component 2020 may be an artificial intelligence-only processor. Alternatively, the first component 2010 may be at least one application, and the second component 2020 may be an operating system (OS). That is, the second component 2020 is more integrated, dedicated, or has a small delay, a performance advantage, or a component having many resources than the first component 2010. A number of operations required when updating or applying may be a component that can be processed more quickly and effectively than the first component 2010.

An interface for transmitting / receiving data between the first component 2010 and the second component 2020 may be defined.

For example, an application program interface (API) having learning data to be applied to a model as an argument value (or an intermediate value or a passing value) may be defined. The API may be a subroutine that can be called for any processing of one protocol (eg, a protocol defined in the electronic device 100) to another protocol (eg, a protocol defined in an external server of the electronic device 100), or It can be defined as a set of functions. That is, an environment in which an operation of another protocol can be performed in one protocol may be provided through an API.

Referring to FIG. 20, a user of the first component 2010 can make a call with a user of another device (S2001).

The first component 2010 may transmit the content of the call between the user and the other party to the second component 2020 (S2003). In this case, the audio data including the call voice is transmitted to the second component 2020, or the text converted to the second component 2020 by processing the speech to text in the first component 2010 Can send.

The second component 2020 may acquire at least one keyword in the currency using the learned artificial intelligence model (S2005). The keyword may be a proper noun of high importance among the proper nouns included in the currency. The importance may be determined based on the frequency of the proper noun, the weight set for the category to which the proper noun belongs.

The second component 2020 may transmit at least one keyword acquired in the call to the first component 2010 (S2007).

The first component 2010 may provide at least one keyword received (S2009).

Specifically, the first component 2010 may provide the received keyword on the call screen, and perform various functions using the keyword in response to the user selecting the keyword. As described above, a search function may be provided or a memo generation function may be provided.

Also, the first component 2010 may determine the recommended application based on the keyword received from the second component 2020, and execute the recommended application in association with the keyword.

21 is a flowchart illustrating a method of controlling an electronic device according to an embodiment of the present disclosure. The flowchart illustrated in FIG. 21 may be configured with operations processed by the electronic device 100 described herein. Therefore, even if omitted, the description of the electronic device 100 may be applied to the flowchart shown in FIG. 21.

Referring to FIG. 21, first, while performing a call with a user of another electronic device using an electronic device, at least one keyword is acquired from the content of a call with the user of the other electronic device (S2110).

Then, the obtained at least one keyword is displayed while the call is being performed (S2120).

In this case, keywords obtained may be displayed on the call screen. According to an embodiment, the keyword may be automatically erased on the call screen according to an algorithm that considers the frequency of mention of the keyword and the time of the last mention.

According to another embodiment, the keyword on the call screen may be moved and destroyed by user interaction (long click and send to the trash).

Then, a search result for a keyword selected by the user is provided from at least one keyword displayed (S2130). Alternatively, a keyword selected by a user among at least one keyword displayed may be stored in the memo application.

The user can designate multiple keywords to search or memo. For example, after touching the first keyword, a keyword to search or memo together may be designated in order, and the electronic device 100 determines that selection of the keyword is ended when a long touch is performed on the last keyword, and thus the first selected keyword From the last selected keyword to the set, you can display a screen to inquire whether to search or take notes.

In addition, the electronic device may predict a scenario that a user can perform after a call and display a UI inquiring whether the user performs a task using a keyword. In addition, when the UI is selected, it is determined that the user agrees to perform the operation, and the operation of inputting a keyword into the application by using the API may be automatically performed.

According to the above-described embodiments, personalized recommendation information can be actively provided from keywords extracted during a call without user intervention, thereby greatly reducing a series of processes that the user has individually performed during and after the call, and thus efficiency. And user satisfaction. In addition, it is possible to provide a service more suited to the usage context based on the content of the call.

Various embodiments described above may be implemented in software, hardware, or a combination thereof. According to a hardware implementation, embodiments described in the present disclosure include application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs) ), Processors, controllers, micro-controllers, microprocessors, and other electrical units for performing functions. In particular, various embodiments described above may be implemented by the processor 130 of the electronic device 100. According to the software implementation, embodiments such as procedures and functions described herein may be implemented as separate software modules. Each of the software modules may perform one or more functions and operations described herein.

Various embodiments of the present disclosure may be implemented with software that includes instructions that can be stored on a machine-readable storage media. A machine is a device that calls a stored command from a storage medium and is operable according to the called command, and may include the electronic device 100 of the disclosed embodiments.

When such instructions are executed by a processor, the processor may perform a function corresponding to the instruction directly or using other components under the control of the processor. Instructions may include code generated or executed by a compiler or interpreter. For example, the instructions stored in the storage medium are executed by the processor, so that the above-described control method of the electronic device 100 can be executed. For example, by executing instructions stored in a storage medium by a processor of a device (or electronic device), at least one of the contents of a call with a user of another electronic device while performing a call with a user of another electronic device using the electronic device A control method comprising obtaining a keyword of, displaying the at least one keyword while the call is being performed, and providing a search result for a keyword selected by a user among the displayed at least one keyword. You can.

The storage medium readable by the device may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' means that the storage medium does not contain a signal and is tangible, but does not distinguish between data being stored semi-permanently or temporarily on the storage medium.

According to one embodiment, a method according to various embodiments disclosed in this document may be provided as being included in a computer program product. Computer program products are commodities that can be traded between sellers and buyers. Computer program products may be distributed online in the form of a storage medium readable by the device (eg compact disc read only memory (CD-ROM)) or through an application store (eg Play Store ™, App Store ™). have. In the case of online distribution, at least a portion of the computer program product may be temporarily stored at least temporarily on a storage medium such as a memory of a manufacturer's server, an application store's server, or a relay server, or may be temporarily generated.

Each component (eg, module or program) according to various embodiments may be composed of a singular or a plurality of entities, and some of the aforementioned sub-components may be omitted, or other sub-components may be various. It may be further included in the embodiment. Alternatively or additionally, some components (eg, modules or programs) may be integrated into one entity, performing the same or similar functions performed by each corresponding component before being integrated. According to various embodiments, operations performed by a module, program, or other component may be sequentially, parallelly, repeatedly, or heuristically executed, at least some operations may be executed in a different order, omitted, or other operations may be added. You can.

Although the preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above, and is usually not limited to the specific subject matter claimed in the claims without departing from the gist of the present disclosure. Of course, various modifications can be made by a person having knowledge of, and these modifications should not be individually understood from the technical idea or prospect of the present disclosure.

100: electronic device

Claims (20)

In the control method of the electronic device,
Obtaining at least one keyword in the content of a call with a user of the other electronic device while performing a call with a user of the other electronic device using the electronic device;
Displaying the at least one keyword while the call is being performed; And
And providing a search result for a keyword selected by the user among the displayed at least one keyword. According to claim 1,
The step of displaying,
A control method of displaying the at least one keyword on a call screen with a user of the other electronic device. According to claim 1,
The step of displaying,
A control method of displaying at least one circular UI element each including the at least one keyword. According to claim 3,
Further comprising the step of determining the importance of the at least one keyword according to the number of times mentioned in the call with the user of the other electronic device;
The step of displaying,
A control method of displaying the size of the at least one circular UI element differently according to the determined importance of the at least one keyword. According to claim 1,
The step of displaying,
If the obtained at least one keyword is plural, control to determine the arrangement interval of the plurality of keywords according to the interval mentioned in the call with the user of the other electronic device, and to display the plurality of keywords according to the determined placement interval Way. According to claim 1,
If the plurality of the at least one keyword is displayed, when receiving a user input for sequentially selecting two or more keywords among the plurality of keywords, determining the selected two or more keywords as a set; further comprising,
The step of providing the search results,
Control method for providing a search result for the determined set. The method of claim 6,
Further comprising the step of displaying a first UI element corresponding to the search function for the determined set and a second UI element corresponding to the memo function for the determined set.
The step of providing the search results,
A control method of providing a search result for the determined set when the first UI element is selected. The method of claim 7,
And when the second UI element is selected, storing the determined set in a memo application. According to claim 1,
The obtaining step,
A control method for acquiring at least one keyword from the content of a call with a user of the other electronic device using the learned artificial intelligence model. According to claim 1,
When a call with the user of the other electronic device ends, determining a recommended application among the plurality of applications of the electronic device based on the obtained at least one keyword; And
And displaying a UI inquiring whether to perform a task related to the determined recommended application and the obtained at least one keyword. In the electronic device,
Communication;
display;
A memory for storing computer executable instructions; And
By executing the computer executable instructions,
While performing a call with a user of another electronic device using the electronic device, obtain at least one keyword from the content of the call with the user of the other electronic device,
Controlling the display to display the at least one keyword while the call is being made,
And a processor that provides a search result for a keyword selected by a user among the displayed at least one keyword. The method of claim 11,
The processor,
An electronic device that controls the display to display the at least one keyword on a call screen with a user of the other electronic device. The method of claim 11,
The processor,
An electronic device that controls the display to display at least one circular UI element each including the at least one keyword. The method of claim 13,
The processor,
The importance of the at least one keyword is determined according to the number of times mentioned in a call with the user of the other electronic device, and the size of the at least one circular UI element is differently displayed according to the determined importance of the at least one keyword An electronic device that controls the display so as to. The method of claim 11,
The processor,
When the obtained at least one keyword is plural, the arrangement interval of the plurality of keywords is determined according to the interval mentioned in the call with the user of the other electronic device, and the plurality of keywords are displayed according to the determined arrangement interval. An electronic device that controls the display. The method of claim 11,
The processor,
When there is a plurality of at least one keyword displayed, when a user input for sequentially selecting two or more keywords among the plurality of keywords is received, the selected two or more keywords are determined as one set, and a search result for the determined set is determined. Electronic devices provided. The method of claim 16,
The processor,
The display is controlled to display a first UI element corresponding to a search function for the determined set and a second UI element corresponding to a memo function for the determined set, and when the first UI element is selected, the determined UI An electronic device that provides search results for. The method of claim 17,
The processor,
When the second UI element is selected, the electronic device stores the determined set in a memo application. The method of claim 11,
The processor,
An electronic device that acquires at least one keyword from a content of a call with a user of the other electronic device using the learned artificial intelligence model. The method of claim 11,
The processor,
When the call with the user of the other electronic device ends, a recommended application is determined among the plurality of applications of the electronic device based on the obtained at least one keyword, and the determined recommended application and the obtained at least one keyword An electronic device that controls the display to display a UI asking whether to perform a related task.

Images